parser.h.svn-base

这是一个用于解析xml文件的类库。使用这个类库

/*
 * Summary: the core parser module
 * Description: Interfaces, constants and types related to the XML parser
 *
 * Copy: See Copyright for the status of this software.
 *
 * Author: Daniel Veillard
 */

#ifndef __XML_PARSER_H__
#define __XML_PARSER_H__

#include <stdarg.h>

#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#include <libxml/dict.h>
#include <libxml/hash.h>
#include <libxml/valid.h>
#include <libxml/entities.h>
#include <libxml/xmlerror.h>
#include <libxml/xmlstring.h>

#ifdef __cplusplus
extern "C" {
#endif

/**
 * XML_DEFAULT_VERSION:
 *
 * The default version of XML used: 1.0
 */
#define XML_DEFAULT_VERSION	"1.0"

/**
 * xmlParserInput:
 *
 * An xmlParserInput is an input flow for the XML processor.
 * Each entity parsed is associated an xmlParserInput (except the
 * few predefined ones). This is the case both for internal entities
 * - in which case the flow is already completely in memory - or
 * external entities - in which case we use the buf structure for
 * progressive reading and I18N conversions to the internal UTF-8 format.
 */

/**
 * xmlParserInputDeallocate:
 * @str:  the string to deallocate
 *
 * Callback for freeing some parser input allocations.
 */
typedef void (* xmlParserInputDeallocate)(xmlChar *str);

struct _xmlParserInput {
    /* Input buffer */
    xmlParserInputBufferPtr buf;      /* UTF-8 encoded buffer */

    const char *filename;             /* The file analyzed, if any */
    const char *directory;            /* the directory/base of the file */
    const xmlChar *base;              /* Base of the array to parse */
    const xmlChar *cur;               /* Current char being parsed */
    const xmlChar *end;               /* end of the array to parse */
    int length;                       /* length if known */
    int line;                         /* Current line */
    int col;                          /* Current column */
    /*
     * NOTE: consumed is only tested for equality in the parser code,
     *       so even if there is an overflow this should not give troubles
     *       for parsing very large instances.
     */
    unsigned long consumed;           /* How many xmlChars already consumed */
    xmlParserInputDeallocate free;    /* function to deallocate the base */
    const xmlChar *encoding;          /* the encoding string for entity */
    const xmlChar *version;           /* the version string for entity */
    int standalone;                   /* Was that entity marked standalone */
    int id;                           /* an unique identifier for the entity */
};

/**
 * xmlParserNodeInfo:
 *
 * The parser can be asked to collect Node informations, i.e. at what
 * place in the file they were detected. 
 * NOTE: This is off by default and not very well tested.
 */
typedef struct _xmlParserNodeInfo xmlParserNodeInfo;
typedef xmlParserNodeInfo *xmlParserNodeInfoPtr;

struct _xmlParserNodeInfo {
  const struct _xmlNode* node;
  /* Position & line # that text that created the node begins & ends on */
  unsigned long begin_pos;
  unsigned long begin_line;
  unsigned long end_pos;
  unsigned long end_line;
};

typedef struct _xmlParserNodeInfoSeq xmlParserNodeInfoSeq;
typedef xmlParserNodeInfoSeq *xmlParserNodeInfoSeqPtr;
struct _xmlParserNodeInfoSeq {
  unsigned long maximum;
  unsigned long length;
  xmlParserNodeInfo* buffer;
};

/**
 * xmlParserInputState:
 *
 * The parser is now working also as a state based parser.
 * The recursive one use the state info for entities processing.
 */
typedef enum {
    XML_PARSER_EOF = -1,	/* nothing is to be parsed */
    XML_PARSER_START = 0,	/* nothing has been parsed */
    XML_PARSER_MISC,		/* Misc* before int subset */
    XML_PARSER_PI,		/* Within a processing instruction */
    XML_PARSER_DTD,		/* within some DTD content */
    XML_PARSER_PROLOG,		/* Misc* after internal subset */
    XML_PARSER_COMMENT,		/* within a comment */
    XML_PARSER_START_TAG,	/* within a start tag */
    XML_PARSER_CONTENT,		/* within the content */
    XML_PARSER_CDATA_SECTION,	/* within a CDATA section */
    XML_PARSER_END_TAG,		/* within a closing tag */
    XML_PARSER_ENTITY_DECL,	/* within an entity declaration */
    XML_PARSER_ENTITY_VALUE,	/* within an entity value in a decl */
    XML_PARSER_ATTRIBUTE_VALUE,	/* within an attribute value */
    XML_PARSER_SYSTEM_LITERAL,	/* within a SYSTEM value */
    XML_PARSER_EPILOG, 		/* the Misc* after the last end tag */
    XML_PARSER_IGNORE,		/* within an IGNORED section */
    XML_PARSER_PUBLIC_LITERAL 	/* within a PUBLIC value */
} xmlParserInputState;

/**
 * XML_DETECT_IDS:
 *
 * Bit in the loadsubset context field to tell to do ID/REFs lookups.
 * Use it to initialize xmlLoadExtDtdDefaultValue.
 */
#define XML_DETECT_IDS		2

/**
 * XML_COMPLETE_ATTRS:
 *
 * Bit in the loadsubset context field to tell to do complete the
 * elements attributes lists with the ones defaulted from the DTDs.
 * Use it to initialize xmlLoadExtDtdDefaultValue.
 */
#define XML_COMPLETE_ATTRS	4

/**
 * XML_SKIP_IDS:
 *
 * Bit in the loadsubset context field to tell to not do ID/REFs registration.
 * Used to initialize xmlLoadExtDtdDefaultValue in some special cases.
 */
#define XML_SKIP_IDS		8

/**
 * xmlParserCtxt:
 *
 * The parser context.
 * NOTE This doesn't completely define the parser state, the (current ?)
 *      design of the parser uses recursive function calls since this allow
 *      and easy mapping from the production rules of the specification
 *      to the actual code. The drawback is that the actual function call
 *      also reflect the parser state. However most of the parsing routines
 *      takes as the only argument the parser context pointer, so migrating
 *      to a state based parser for progressive parsing shouldn't be too hard.
 */
struct _xmlParserCtxt {
    struct _xmlSAXHandler *sax;       /* The SAX handler */
    void            *userData;        /* For SAX interface only, used by DOM build */
    xmlDocPtr           myDoc;        /* the document being built */
    int            wellFormed;        /* is the document well formed */
    int       replaceEntities;        /* shall we replace entities ? */
    const xmlChar    *version;        /* the XML version string */
    const xmlChar   *encoding;        /* the declared encoding, if any */
    int            standalone;        /* standalone document */
    int                  html;        /* an HTML(1)/Docbook(2) document */

    /* Input stream stack */
    xmlParserInputPtr  input;         /* Current input stream */
    int                inputNr;       /* Number of current input streams */
    int                inputMax;      /* Max number of input streams */
    xmlParserInputPtr *inputTab;      /* stack of inputs */

    /* Node analysis stack only used for DOM building */
    xmlNodePtr         node;          /* Current parsed Node */
    int                nodeNr;        /* Depth of the parsing stack */
    int                nodeMax;       /* Max depth of the parsing stack */
    xmlNodePtr        *nodeTab;       /* array of nodes */

    int record_info;                  /* Whether node info should be kept */
    xmlParserNodeInfoSeq node_seq;    /* info about each node parsed */

    int errNo;                        /* error code */

    int     hasExternalSubset;        /* reference and external subset */
    int             hasPErefs;        /* the internal subset has PE refs */
    int              external;        /* are we parsing an external entity */

    int                 valid;        /* is the document valid */
    int              validate;        /* shall we try to validate ? */
    xmlValidCtxt        vctxt;        /* The validity context */

    xmlParserInputState instate;      /* current type of input */
    int                 token;        /* next char look-ahead */    

    char           *directory;        /* the data directory */

    /* Node name stack */
    const xmlChar     *name;          /* Current parsed Node */
    int                nameNr;        /* Depth of the parsing stack */
    int                nameMax;       /* Max depth of the parsing stack */
    const xmlChar *   *nameTab;       /* array of nodes */

    long               nbChars;       /* number of xmlChar processed */
    long            checkIndex;       /* used by progressive parsing lookup */
    int             keepBlanks;       /* ugly but ... */
    int             disableSAX;       /* SAX callbacks are disabled */
    int               inSubset;       /* Parsing is in int 1/ext 2 subset */
    const xmlChar *    intSubName;    /* name of subset */
    xmlChar *          extSubURI;     /* URI of external subset */
    xmlChar *          extSubSystem;  /* SYSTEM ID of external subset */

    /* xml:space values */
    int *              space;         /* Should the parser preserve spaces */
    int                spaceNr;       /* Depth of the parsing stack */
    int                spaceMax;      /* Max depth of the parsing stack */
    int *              spaceTab;      /* array of space infos */

    int                depth;         /* to prevent entity substitution loops */
    xmlParserInputPtr  entity;        /* used to check entities boundaries */
    int                charset;       /* encoding of the in-memory content
				         actually an xmlCharEncoding */
    int                nodelen;       /* Those two fields are there to */
    int                nodemem;       /* Speed up large node parsing */
    int                pedantic;      /* signal pedantic warnings */
    void              *_private;      /* For user data, libxml won't touch it */

    int                loadsubset;    /* should the external subset be loaded */
    int                linenumbers;   /* set line number in element content */
    void              *catalogs;       /* document's own catalog */
    int                recovery;      /* run in recovery mode */
    int                progressive;   /* is this a progressive parsing */
    xmlDictPtr         dict;          /* dictionnary for the parser */
    const xmlChar *   *atts;          /* array for the attributes callbacks */
    int                maxatts;       /* the size of the array */
    int                docdict;       /* use strings from dict to build tree */

    /*
     * pre-interned strings
     */
    const xmlChar *str_xml;
    const xmlChar *str_xmlns;
    const xmlChar *str_xml_ns;

    /*
     * Everything below is used only by the new SAX mode
     */
    int                sax2;          /* operating in the new SAX mode */
    int                nsNr;          /* the number of inherited namespaces */
    int                nsMax;         /* the size of the arrays */
    const xmlChar *   *nsTab;         /* the array of prefix/namespace name */
    int               *attallocs;     /* which attribute were allocated */
    void *            *pushTab;       /* array of data for push */
    xmlHashTablePtr    attsDefault;   /* defaulted attributes if any */
    xmlHashTablePtr    attsSpecial;   /* non-CDATA attributes if any */
    int                nsWellFormed;  /* is the document XML Nanespace okay */
    int                options;       /* Extra options */

    /*
     * Those fields are needed only for treaming parsing so far
     */
    int               dictNames;    /* Use dictionary names for the tree */
    int               freeElemsNr;  /* number of freed element nodes */
    xmlNodePtr        freeElems;    /* List of freed element nodes */
    int               freeAttrsNr;  /* number of freed attributes nodes */
    xmlAttrPtr        freeAttrs;    /* List of freed attributes nodes */

    /*
     * the complete error informations for the last error.
     */
    xmlError          lastError;
};

/**
 * xmlSAXLocator:
 *
 * A SAX Locator.
 */
struct _xmlSAXLocator {
    const xmlChar *(*getPublicId)(void *ctx);
    const xmlChar *(*getSystemId)(void *ctx);
    int (*getLineNumber)(void *ctx);
    int (*getColumnNumber)(void *ctx);
};

/**
 * xmlSAXHandler:
 *
 * A SAX handler is bunch of callbacks called by the parser when processing
 * of the input generate data or structure informations.
 */

/**
 * resolveEntitySAXFunc:
 * @ctx:  the user data (XML parser context)
 * @publicId: The public ID of the entity
 * @systemId: The system ID of the entity
 *
 * Callback:
 * The entity loader, to control the loading of external entities,
 * the application can either:
 *    - override this resolveEntity() callback in the SAX block
 *    - or better use the xmlSetExternalEntityLoader() function to
 *      set up it's own entity resolution routine
 *
 * Returns the xmlParserInputPtr if inlined or NULL for DOM behaviour.
 */
typedef xmlParserInputPtr (*resolveEntitySAXFunc) (void *ctx,
				const xmlChar *publicId,
				const xmlChar *systemId);
/**
 * internalSubsetSAXFunc:
 * @ctx:  the user data (XML parser context)
 * @name:  the root element name
 * @ExternalID:  the external ID
 * @SystemID:  the SYSTEM ID (e.g. filename or URL)
 *
 * Callback on internal subset declaration.
 */
typedef void (*internalSubsetSAXFunc) (void *ctx,
				const xmlChar *name,
				const xmlChar *ExternalID,
				const xmlChar *SystemID);
/**
 * externalSubsetSAXFunc:
 * @ctx:  the user data (XML parser context)
 * @name:  the root element name
 * @ExternalID:  the external ID
 * @SystemID:  the SYSTEM ID (e.g. filename or URL)
 *
 * Callback on external subset declaration.
 */
typedef void (*externalSubsetSAXFunc) (void *ctx,
				const xmlChar *name,
				const xmlChar *ExternalID,
				const xmlChar *SystemID);
/**
 * getEntitySAXFunc:
 * @ctx:  the user data (XML parser context)
 * @name: The entity name
 *
 * Get an entity by name.
 *
 * Returns the xmlEntityPtr if found.
 */
typedef xmlEntityPtr (*getEntitySAXFunc) (void *ctx,
				const xmlChar *name);
/**
 * getParameterEntitySAXFunc:
 * @ctx:  the user data (XML parser context)
 * @name: The entity name
 *
 * Get a parameter entity by name.
 *
 * Returns the xmlEntityPtr if found.
 */
typedef xmlEntityPtr (*getParameterEntitySAXFunc) (void *ctx,
				const xmlChar *name);
/**
 * entityDeclSAXFunc:
 * @ctx:  the user data (XML parser context)
 * @name:  the entity name 
 * @type:  the entity type 
 * @publicId: The public ID of the entity
 * @systemId: The system ID of the entity